Azure models
Route requests to Azure through Vercel AI Gateway. Compare the models Azure serves, with unified billing and automatic failover across providers.
| Model | Context | Input | Output | Latency | Throughput | Cache | Search | Capabilities | ZDR | No Training | Regional Inference | Free AI Gateway Credit | Released |
|---|
| — | $22/M chars | — | — | — | — | — | 10/01/2026 | ||||||
| — | $15/M chars | — | — | — | — | — | 10/01/2026 | ||||||
| — | $0.54/hr | — | — | — | — | — | 10/01/2026 | ||||||
| 1.1M | $2/M+1 more | $10/M+1 more | 3.2 s | 78 tps | Read$0.10/M Write$2.50/M | $14/K | +5 | 09/29/2026 | |||||
| 1.1M | $0.10/M+1 more | $0.50/M+1 more | 3.5 s | 155 tps | Read$0.01/M Write$0.13/M | $14/K | +5 | 09/22/2026 | |||||
| 1.1M | $2/M+1 more | $10/M+1 more | 2.3 s | 135 tps | Read$0.20/M Write$2.50/M | $14/K | +5 | 09/22/2026 | |||||
| 1.1M | $10/M+1 more | $50/M+1 more | 3.5 s | 47 tps | Read$1/M Write$12.50/M | $14/K | +6 | 09/04/2026 | |||||
| — | $0.10/hr | — | — | — | — | — | 09/03/2026 | ||||||
| — | $15/M chars | — | — | — | — | — | 07/23/2026 | ||||||
| 1.1M | $0.20/M+1 more | $1.20/M+1 more | 3.4 s | 161 tps | Read$0.02/M Write$0.25/M | $14/K | +5 | 07/09/2026 | |||||
| 1.1M | $5/M+1 more | $30/M+1 more | 4.8 s | 121 tps | Read$0.50/M Write$6.25/M | $14/K | +5 | 07/09/2026 | |||||
| 1.1M | $2/M+1 more | $12/M+1 more | 1.0 s | — | Read$0.20/M Write$2.50/M | $14/K | +5 | 07/09/2026 | |||||
| — | $22/M chars | — | — | — | — | — | 06/02/2026 | ||||||
| 272K | $5/M+1 more | $30/M+1 more | 4.5 s | 121 tps | Read$0.50/M | $14/K | +4 | 04/24/2026 | |||||
| 1M | $0.19/M | $0.51/M | 1.1 s | 136 tps | Read$0.03/M | — | +1 | 04/23/2026 | |||||
| 1M | $1.74/M | $3.48/M | 2.7 s | 146 tps | Read$0.15/M | — | +1 | 04/23/2026 | |||||
| 400K | $0.75/M | $4.50/M | 1.4 s | 114 tps | Read$0.08/M | $14/K | +4 | 03/17/2026 | |||||
| 400K | $0.20/M | $1.25/M | 1.0 s | 72 tps | Read$0.02/M | $14/K | +4 | 03/17/2026 | |||||
| 1M | $2.50/M+1 more | $15/M+1 more | 4.3 s | 64 tps | Read$0.25/M | $14/K | +4 | 03/05/2026 | |||||
| 1M | $30/M+1 more | $180/M+1 more | — | — | — | $14/K | +3 | 03/05/2026 | |||||
| 400K | $1.75/M | $14/M | 0.7 s | — | Read$0.18/M | $14/K | +4 | 02/05/2026 | |||||
| 400K | $1.75/M | $14/M | 0.6 s | — | Read$0.18/M | $14/K | +4 | 12/18/2025 | |||||
| 400K | $1.75/M | $14/M | 1.0 s | 86 tps | Read$0.18/M | $14/K | +4 | 12/11/2025 | |||||
| 400K | $1.25/M | $10/M | 2.6 s | — | Read$0.13/M | $14/K | +4 | 11/19/2025 | |||||
| 400K | $1.25/M | $10/M | 1.5 s | — | Read$0.13/M | $14/K | +4 | 11/12/2025 | |||||
| 400K | $1.25/M | $10/M | 0.9 s | — | Read$0.13/M | $14/K | +4 | 11/12/2025 | |||||
| 400K | $0.25/M | $2/M | 0.5 s | — | Read$0.03/M | $14/K | +4 | 11/12/2025 | |||||
| 400K | $1.25/M | $10/M | 0.7 s | 175 tps | Read$0.13/M | $14/K | +4 | 09/15/2025 | |||||
| 400K | $0.05/M | $0.40/M | — | 162 tps | Read$0.01/M | $14/K | +4 | 08/07/2025 | |||||
| 400K | $0.25/M | $2/M | 1.7 s | 122 tps | Read$0.03/M | $14/K | +4 | 08/07/2025 | |||||